Sign Up to like & get
recommendations!
1
Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3160451
Abstract: A portion of the data in video captioning datasets are noisy and unsuitable for models to learn at early stages, e.g., there could be a generic 4-word-long caption lacking distinctive details of video content and…
read more here.
Keywords:
curriculum learning;
adaptive curriculum;
learning video;
video captioning ... See more keywords